• Publications
  • Influence
Gaussian Process Optimization in the Bandit Setting: No Regret and Experimental Design
TLDR
This work analyzes GP-UCB, an intuitive upper-confidence based algorithm, and bound its cumulative regret in terms of maximal information gain, establishing a novel connection between GP optimization and experimental design and obtaining explicit sublinear regret bounds for many commonly used covariance functions.
Cost-effective outbreak detection in networks
TLDR
This work exploits submodularity to develop an efficient algorithm that scales to large problems, achieving near optimal placements, while being 700 times faster than a simple greedy algorithm and achieving speedups and savings in storage of several orders of magnitude.
Near-Optimal Sensor Placements in Gaussian Processes: Theory, Efficient Algorithms and Empirical Studies
TLDR
It is proved that the problem of finding the configuration that maximizes mutual information is NP-complete, and a polynomial-time approximation is described that is within (1-1/e) of the optimum by exploiting the submodularity of mutual information.
Adaptive Submodularity: Theory and Applications in Active Learning and Stochastic Optimization
TLDR
It is proved that if a problem satisfies adaptive submodularity, a simple adaptive greedy algorithm is guaranteed to be competitive with the optimal policy, providing performance guarantees for both stochastic maximization and coverage.
Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting
TLDR
This work analyzes an intuitive Gaussian process upper confidence bound algorithm, and bound its cumulative regret in terms of maximal in- formation gain, establishing a novel connection between GP optimization and experimental design and obtaining explicit sublinear regret bounds for many commonly used covariance functions.
Submodular Function Maximization
TLDR
This survey will introduce submodularity and some of its generalizations, illustrate how it arises in various applications, and discuss algorithms for optimizing submodular functions.
Streaming submodular maximization: massive data summarization on the fly
TLDR
This paper develops the first efficient streaming algorithm with constant factor 1/2-ε approximation guarantee to the optimum solution, requiring only a single pass through the data, and memory independent of data size.
Lazier Than Lazy Greedy
TLDR
The first linear-time algorithm for maximizing a general monotone submodular function subject to a cardinality constraint is developed, and it is shown that the randomized algorithm, STOCHASTIC-GREEDY, can achieve a (1 — 1/e — e) approximation guarantee, in expectation, to the optimum solution in time linear in the size of the data.
Robust Submodular Observation Selection
In many applications, one has to actively select among a set of expensive observations before making an informed decision. For example, in environmental monitoring, we want to select locations to
...
1
2
3
4
5
...